A Multivariate Kernel Approach to Forecasting the Variance Covariance of Stock Market Returns

Ralf Becker, Adam Clements, Robert O'Neill

Research output: Contribution to journalArticle

Abstract

This paper introduces a multivariate kernel based forecasting tool for the prediction of variance-covariance matrices of stock returns. The method introduced allows for the incorporation of macroeconomic variables into the forecasting process of the matrix without resorting to a decomposition of the matrix. The model makes use of similarity forecasting techniques and it is demonstrated that several popular techniques can be thought as a subset of this approach. A forecasting experiment demonstrates the potential for the technique to improve the statistical accuracy of forecasts of variance-covariance matrices.
Original languageEnglish
Article number7
Pages (from-to)1-27
Number of pages27
JournalEconometrics
Volume6
Issue number1
Early online date17 Feb 2018
DOIs
Publication statusPublished - Mar 2018

Fingerprint

Stock market returns
Kernel
Covariance matrix
Prediction
Stock returns
Decomposition
Macroeconomic variables
Experiment

Cite this

@article{4be91d01e708485884464709b41c442c,
title = "A Multivariate Kernel Approach to Forecasting the Variance Covariance of Stock Market Returns",
abstract = "This paper introduces a multivariate kernel based forecasting tool for the prediction of variance-covariance matrices of stock returns. The method introduced allows for the incorporation of macroeconomic variables into the forecasting process of the matrix without resorting to a decomposition of the matrix. The model makes use of similarity forecasting techniques and it is demonstrated that several popular techniques can be thought as a subset of this approach. A forecasting experiment demonstrates the potential for the technique to improve the statistical accuracy of forecasts of variance-covariance matrices.",
keywords = "Volatility forecasting, Kernel density estimation, Similarity forecasting",
author = "Ralf Becker and Adam Clements and Robert O'Neill",
year = "2018",
month = "3",
doi = "10.3390/econometrics6010007",
language = "English",
volume = "6",
pages = "1--27",
journal = "Econometrics",
number = "1",

}

A Multivariate Kernel Approach to Forecasting the Variance Covariance of Stock Market Returns. / Becker, Ralf ; Clements, Adam; O'Neill, Robert.

In: Econometrics, Vol. 6, No. 1, 7, 03.2018, p. 1-27.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A Multivariate Kernel Approach to Forecasting the Variance Covariance of Stock Market Returns

AU - Becker, Ralf

AU - Clements, Adam

AU - O'Neill, Robert

PY - 2018/3

Y1 - 2018/3

N2 - This paper introduces a multivariate kernel based forecasting tool for the prediction of variance-covariance matrices of stock returns. The method introduced allows for the incorporation of macroeconomic variables into the forecasting process of the matrix without resorting to a decomposition of the matrix. The model makes use of similarity forecasting techniques and it is demonstrated that several popular techniques can be thought as a subset of this approach. A forecasting experiment demonstrates the potential for the technique to improve the statistical accuracy of forecasts of variance-covariance matrices.

AB - This paper introduces a multivariate kernel based forecasting tool for the prediction of variance-covariance matrices of stock returns. The method introduced allows for the incorporation of macroeconomic variables into the forecasting process of the matrix without resorting to a decomposition of the matrix. The model makes use of similarity forecasting techniques and it is demonstrated that several popular techniques can be thought as a subset of this approach. A forecasting experiment demonstrates the potential for the technique to improve the statistical accuracy of forecasts of variance-covariance matrices.

KW - Volatility forecasting

KW - Kernel density estimation

KW - Similarity forecasting

UR - http://www.scopus.com/inward/record.url?scp=85056765680&partnerID=8YFLogxK

U2 - 10.3390/econometrics6010007

DO - 10.3390/econometrics6010007

M3 - Article

VL - 6

SP - 1

EP - 27

JO - Econometrics

JF - Econometrics

IS - 1

M1 - 7

ER -